New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add support for Dot product Similarity #86

Open

Taenerys opened this issue Nov 9, 2024 · 1 comment · May be fixed by #120

Labels

good first issue

Taenerys commented Nov 9, 2024

Context: Currently we have only implemented Euclidean Distance (L2 norm) (can read more about it from l2.rs file in Utils module)

As a starting point to get familiar with the codebase, we want to implement Dot product Similarity. Resources:
https://www.pinecone.io/learn/vector-similarity/
https://tivadardanka.com/blog/how-the-dot-product-measures-similarity

Acceptance:

Add unit tests
Add benchmark tests

The text was updated successfully, but these errors were encountered:

Taenerys self-assigned this

Author

Taenerys commented Nov 14, 2024

For my personal learning and research:

Rust: https://practice.course.rs/why-exercise.html
Good resource on SIMD and Rust: https://calebzulawski.github.io/rust-simd-book/2-portable-simd.html
Computer Architecture - a Quantitative Approach: https://acs.pub.ro/~cpop/SMPA/Computer%20Architecture%20A%20Quantitative%20Approach%20(5th%20edition).pdf

Taenerys linked a pull request

that will close this issue

[DRAFT] Implement Dot Product Similarity Distance algorithm #120

Open

hicder added the good first issue label

hicder unassigned Taenerys

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment